{"id":24757469,"url":"https://github.com/cpu-ds/coursegraph","last_synced_at":"2025-10-11T04:31:16.000Z","repository":{"id":247948395,"uuid":"826786121","full_name":"CPU-DS/CourseGraph","owner":"CPU-DS","description":"使用大模型自动构建课程知识图谱","archived":false,"fork":false,"pushed_at":"2025-01-21T09:14:50.000Z","size":179794,"stargazers_count":10,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"dev","last_synced_at":"2025-01-28T15:14:59.900Z","etag":null,"topics":["knowledge-graph","llm"],"latest_commit_sha":null,"homepage":"https://cpu-ds.github.io/CourseGraph/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CPU-DS.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-07-10T11:26:20.000Z","updated_at":"2025-01-21T09:14:54.000Z","dependencies_parsed_at":"2024-12-28T09:33:40.522Z","dependency_job_id":null,"html_url":"https://github.com/CPU-DS/CourseGraph","commit_stats":null,"previous_names":["wangtao2001/coursekg","wangtao2001/coursegraph","cpu-ds/coursegraph"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CPU-DS%2FCourseGraph","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CPU-DS%2FCourseGraph/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CPU-DS%2FCourseGraph/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CPU-DS%2FCourseGraph/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CPU-DS","download_url":"https://codeload.github.com/CPU-DS/CourseGraph/tar.gz/refs/heads/dev","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":236035497,"owners_count":19084697,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["knowledge-graph","llm"],"created_at":"2025-01-28T15:15:13.169Z","updated_at":"2025-10-11T04:31:05.990Z","avatar_url":"https://github.com/CPU-DS.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"docs/public/logo.png\" width=\"200\"  alt=\"\" /\u003e\n\u003ch2\u003eCourseGraph: 使用大模型自动构建课程知识图谱\u003c/h2\u003e\n\n\u003cp\u003e\n    \u003cb\u003e中文\u003c/b\u003e | \u003ca href=\"README_en.md\"\u003eEnglish\u003c/a\u003e\n\u003c/p\u003e\n\u003c/div\u003e\n\nCourseGraph 使用大模型，利用多种 prompt 优化技术, 自动从教材、书籍中抽取知识点, 构成以课程-章节-知识点为主题的知识图谱。为增加每个知识点的信息, CourseGraph 可以为知识点链接相应的习题、扩展阅读材料等资源, 另外也可利用多模态大模型从 pptx、图片、视频中提取信息并与之相关联。\n\n## 🤔 局限性\n\n- 目前只实现了基本的知识图谱抽取和对 pptx 的解析，效果有待优化\n- 对视频的解析还处于规划中\n\n## 📈 未来发展方向\n\n- 改进提示词工程，并尝试使用 Agent 完成相关工作\n- 基于图谱的问答 (KBQA 或 Graph-RAG)\n\n## 🚀 快速使用\n\n首先申请阿里云通义千问 [API Key](https://help.aliyun.com/zh/model-studio/developer-reference/get-api-key)，然后选择使用本地安装或使用 Docker 安装：\n\n### 方式一：本地安装\n\n#### 安装依赖\n\n请确保已安装 [Anaconda](https://www.anaconda.com/) (或 [Miniconda](https://docs.conda.io/en/miniconda.html))、[Neo4j](https://neo4j.com/) 和 [Rust](https://www.rust-lang.org/) ，然后执行：\n\n```bash\ngit clone git@github.com:CPU-DS/CourseGraph.git\ncd CourseGraph\nconda create -n cg python=3.10 -y\nconda activate cg\npip install poetry\npoetry config virtualenvs.create false\npoetry install\ncd rust\nmaturin develop\ncd ..\n```\n\nLinux 下还需安装 libreoffice 以完成文档转换，以 Debian 系为例：\n\n```bash\nsudo apt install libreoffice\n```\n\n#### 执行示例\n\n提供 Neo4j 连接地址、用户名和密码，然后执行：\n\n```bash\npython examples/get_knowledge_graph.py -u bolt://localhost:7687 -n neo4j -p neo4j\n```\n\n### 方式二：使用 Docker 安装\n\n```bash\ngit clone git@github.com:wangtao2001/CourseGraph.git\ncd CourseGraph\nexport DASHSCOPE_API_KEY=\ndocker-compose -f docker/docker-compose.yml up -d\npython examples/get_knowledge_graph.py\n```\n\n## 📚 文档\n\n可以在 `docs` 目录下查看文档, 也可以访问 [在线文档](https://CPU-DS.github.io/CourseGraph/) (由于项目功能仍处于快速开发中，故在线文档暂时还没有准备好)。\n\n如果你希望自定义在线文档请依照以下步骤：\n\n#### 依赖安装和预览\n\n文档使用 [VitePress](https://vitepress.dev/) 构建, 需安装 [Node.js](https://nodejs.org/) 18 或以上版本，然后执行：\n\n```bash\ncd docs\nnpm i\nnpm run docs:dev\n```\n\n使用浏览器打开 [http://localhost:5173/](http://localhost:5173/) 即可进行预览。\n\n\n## 🛠️ 贡献、协议和引用\n\n欢迎提交 [PR](https://github.com/CPU-DS/CourseGraph/pulls) 或 [Issues](https://github.com/CPU-DS/CourseGraph/issues)，也欢迎参与任何形式的贡献。\n\n本项目基于 [MIT 协议](LICENSE) 开源。同时若觉得 CourseGraph 项目有助于你的工作，也请参考 [CITATION.cff](CITATION.cff) 文件 (或点击 Repository 右侧的 `Cite this repository` 按钮) 进行引用。\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcpu-ds%2Fcoursegraph","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcpu-ds%2Fcoursegraph","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcpu-ds%2Fcoursegraph/lists"}